Preipheral Urban Spaces Development

Preipheral Urban Spaces Development

Analyzing Peri-Urban Settlement Growth in the Southern Fringe of Tehran Metropolitan Area Using Global and Local Spatial Data Mining

Document Type : Original Article

Authors
Soraya Rostami 1
Babak Mirbagheri 2
Ali Akbar Matkan 3
1 M.Sc., Center for Remote Sensing and GIS Research, Faculti of Earth Sciences, Shahid Beheshti University, Tehran, Iran
2 Assistant Prof., Center for Remote Sensing and GIS Research, Faculti of Earth Sciences, Shahid Beheshti University, Tehran, Iran.
3 Prof., Center for Remote Sensing and GIS Research, Faculti of Earth Sciences, Shahid Beheshti University, Tehran, Iran.
10.22034/jpusd.2025.525245.1346
Abstract
Extended Abstract
Introduction
Spatial data mining is an effective method and tool for extracting information and discovering knowledge from large spatial databases, serving as a crucial foundation for informed decision-making and sustainable urban planning and management. The present study aims to uncover spatial patterns related to the growth of peri-urban areas in the metropolis of Tehran. Metropolises are essentially the product of uneven development and the convergent flow of power concentration, capital accumulation, and the densification of population and activities at national and regional scales. As the converging trends of population and activity growth intensify, the demand for land and space also increases. The rising demand to supply land for the growing population and activities has led to a divergence in the redistribution of population and activities at the local scale and in the peripheries of metropolises. This trend fosters conditions for dispersed growth and fragmented expansion of peri-urban areas. Urban and rural settlements, as well as built-up spaces located in the southern urban fringe of Tehran, have also developed within this broader framework. The present research revolves around two main topics: 
1. Detecting land-use changes between 2001 and 2021 
2. Analyzing the growth of built-up spaces in the southern periphery of Tehran through spatial data mining and employing global and local spatial association rule. 
 
Methodology 
The present study adopts a quantitative approach within its macro-methodological framework. It is an applied study in terms of its purpose and descriptive-analytical in terms of its methodology. The primary data used in this research include demographic data from the Statistical Center of Iran, existing administrative division maps, 1:25,000 topographic maps, online maps from OpenStreetMap (OSM), as well as images from the TM, ETM+, and OLI sensors of the Landsat satellite for the years 2001 and 2021. Initially, within the Google Earth Engine platform and using the Random Forest algorithm, satellite images were classified to prepare land use and land cover maps for each year. The extraction of association rules was based on the Apriori algorithm. The Apriori algorithm extract association rules through two stages: "identifying a set of frequent items" and "determining the relationships between the identified frequent items." In this study, the Apriori algorithm was used to extract association rules at both a global scale for the entire study area and a local scale (counties within the study area).  The variables used in this analysis include: 
- Distance from built-up areas in urban and rural zones 
- Distance from main roads leading to settlements 
- Distance from industrial land uses and workshop complexes, and 
- Land use type (agricultural/barren) in 2001. 
Then, a potential (probability) map of urban built-up area expansion was generated using the derived association rules and confidence values of land use change susceptibility between 2001 and 2021. This map illustrates the confidence values with which land use changes followed the trend of conversion to built-up areas during the 2001–2021 period.
 
Results and Discussion 
The land use and land cover maps produced over the 20-year study period indicate that 270.8 square kilometers have been added to urban, rural, and industrial built-up areas, with their share of the total area increasing from 2.3% in 2001 to 11.5% in 2021. Association rules also reveal that distance from urban built-up areas played the most significant role in land use changes. Within a 100-meter distance from urban built-up areas, the likelihood of land use change was considerably higher in the counties of Shahriar, Robat Karim, Rey, Qods, Eslamshahr, and Baharestan (confidence values: 85% to 97%). In contrast, association rules indicate that in most counties beyond 900 meters, the probability of no land use change increases (confidence values: 55% to 91%). Additionally, the research findings show an inverse relationship between distance from roads and land use change, with the probability of change increasing as the distance decreases. Accordingly, lands near roads (within 100 meters) are more likely to undergo land use change (confidence: 65% to 88%) and this probability decreases with greater distance. As a result, lands far from roads (beyond 900 meters) in Rey, Shahriar, and Robat Karim counties have a very high likelihood (confidence: 82% to 94%) of not being subject to land use change. The maps generated based on global association rules related to the expansion of built-up areas over the 20-year period (2001–2021) show that lands with medium confidence (0.407 to 0.763) and high confidence (0.764 to 0.968) were more susceptible to land use change. A comparison of association rules on a global and local scale also showed that the counties of Shahriar, Shahr-e Rey, and Robat Karim shared more than 50% of their rules with global rules, while in the three counties of Islamshahr, Qods, and Baharestan, the common rules with global rules were less than 50%.
 
Conclusion 
The final results of land use change detection between 2001 and 2021 reveal that built-up areas have significantly expanded and exhibit an increasing tendency toward spatial continuity. Additionally, association rules related to land use changes from 2001 to 2021 highlight the capabilities of data mining techniques in analyzing land use changes at both global and local scales. Moreover, the extracted rules indicate that proximity to urban built-up areas and road networks significantly increases the likelihood of land use change. These changes reflect the degradation of ecological infrastructures, particularly agricultural and orchard lands in the southern periphery of Tehran, which serve as a key component of the suburban ecosystem. The continuation and intensification of this urban expansion trend in the southern buffer zone of Tehran could signal the formation of a continuous urban expanse, especially in the northern part of the study area, merging with Tehran’s urban fabric. This reality must be taken as a serious warning, necessitating strict monitoring and regulation of construction activities in the region.
 
Funding
According to the responsible author, this article has no financial support
 
Authors’ Contribution
Authors contributed equally to the conceptualization and writing of the article. All of the authors approved thecontent of the manuscript and agreed on all aspects of the work declaration of competing interest none.
 
Conflict of Interest
Authors declared no conflict of interest.
 
Acknowledgments
 We are grateful to all the scientific consultants of this paper. The authors are sincerely grateful to the participants who took part in the study.
Keywords
Spatial data mining
Association rules
Peri-Urban settlement
Land use change
Local analysis

Subjects

اکبری، عطاالله و اسکندری­ثانی، محمد و اسماعیل­نژاد، مرتضی. (1402). شبیه‌سازی و پیش‌بینی الگوی رشد شهری تا سال 1430 با استفاده از مدل SLEUTH-3R  (مطالعه موردی: شهر زاهدان)، نشریه جغرافیا و توسعه ناحیه‌ای، (1)21، 142-105.
امیرانتخابی، شهرام؛ جوان، فرهاد و حسنی مقدم، حسن. (1397). تحلیل اثرات خزش شهری در ناپایداری سکونتگاه­های روستایی (مورد مطالعه: شهرستان رضوانشهر). مهندسی جغرافیایی سرزمین، 2(3)، 59-71.
بهاری سجهرود، زهرا و طالعی، محمد. (1400). داده‌کاوی و کاوش وضع موجود الگوی مکانی استقرار کاربری‌های شهری، اطلاعات جغرافیایی سپهر، 3(119)، 86-75.
جوان، فرهاد؛ حسنی مقدم، حسن و ترابی، حسن. (1399). ارزیابی روند تخریب اراضی جنگلی با استفاده از الگوریتم شبکه عصبی مصنوعی (مورد مطالعه: جنگل های فندقلو شهرستان نمین). محیط زیست و توسعه فرابخشی، 5(69)، 63-74.
خلیلی، احمد،  زبردست، اسفندیار و عزیزی، محمدمهدی. (1397). گونه‌شناسی فضایی الگوهای رشد در مناطق شهر بنیان. نشریه هنرهای زیبا: معماری و شهرسازی، (2)23، 66-53.
خیرآبادی، مسعود، شهرهای ایران، ترجمه حسین حاتمی‌نژاد و عزت‌اله مافی، مشهد، نشر نیکا.
دولت‌آبادی، فیروز و مرادپور، نبی. (1398). بررسی و مدل­سازی تغییرات کاربری زمین شهر خرم‌آباد تا سال 1404 با استفاده از مدل‌های MLP، MARKOV و CA-MARCOV، نشریه مدیریت شهری، (53)17، 368-351.
رهنمایی، محمدتقی. (1371). مجموعه مباحث شهرسازی: جغرافیا، تهران، انتشارات مرکز تحقیقات شهرسازی و معماری ایران.
زمانی، زهرا، علی محمدی، عباس و فرنقی، مهدی. (1398). بررسی ارتباط بین اطلاعات و ویژگی‌های مکانی و جمعیتی با مصرف آب در شهر اصفهان با استفاده از کاوش قوانین انجمنی، نشریه علوم و فنون نقشه‌برداری، (1)9، 81-65.
طرح جامع شهر تهران. (1386). مرکز مطالعات و برنامه‌ریزی شهر تهران.
مسعودی، کیومرث. (1389). مطالعات و ساماندهی باغ‌ها و اراضی مزروعی شهر تهران: مطالعات جمعیتی- اجتماعی، مهندسان مشاور بافت شهر.
میرباقری، بابک و علی­محمدی، عباس. (1397). ارزیابی قابلیت رگرسیون وزنی جغرافیایی در بهبود پیش‌بینی رشد اراضی شهری با استفاده از سلول‌های خودکار. مهندسی فناوری اطلاعات مکانی، 6(2 )، 43-64.
نصیری هنده خاله، اسماعیل؛ جوان، فرهاد و یونسی سندی، ریحانه. (1401). بررسی تاثیرات خزش شهری بندر انزلی در پایداری کالبدی –فضایی سکونتگاه­های پیراشهری. روستا و توسعه پایدار فضا، 3(4)، 82-98.
یوسفی‌فر، شهرام. (1389). الگوهای پیدایش شهر و شهرنشینی در تاریخ ایران، مجله تاریخ ایران، 170-145، (1)3.
Agrawal, R., Imieliński, T., & Swami, A. (1993, June). Mining association rules between sets of items in large databases. In Proceedings of the 1993 ACM SIGMOD international conference on Management of data (pp. 207-216).
Angel, S., Sheppard, S., Civco, D. L., Buckley, R., Chabaeva, A., Gitlin, L., ... & Perlin, M. (2005). The dynamics of global urban expansion (p. 205). Washington, DC: World Bank, Transport and Urban Development Department.
Bibri, S. E. (2018). Data science for urban sustainability: Data mining and data-analytic thinking in the next wave of city analytics.
Bivand, R. S., & Wong, D. W. (2018). Comparing implementations of global and local indicators of spatial association. Test, 27(3), 716-748.
Cai, Fei, Jie Chen, Telin Chen, Banghua Zhang, and Wenping Fan. "Mining significant local spatial association rules for multi-category point data." Heliyon 10, no. 3 (2024).
Dietzel, C., Oguz, H., Hemphill, J. J., Clarke, K. C., & Gazulis, N. (2005). Diffusion and coalescence of the Houston Metropolitan Area: evidence supporting a new urban theory. Environment and Planning B: Planning and Design, 32(2), 231-246.
Geurts, K., Wets, G., Brijs, T., & Vanhoof, K. (2003). Profiling of high-frequency accident locations by use of association rules. Transportation research record, 1840(1), 123-130
Han, D., Shi, Y., Wang, W., & Dai, Y. (2013). Research on Multi-Level Association Rules Based on Geosciences Data. J. Softw., 8(12), 3269-3276.
Houshmand-Nanehkaran, F., Lajevardi, S. M., & Mahlouji-Bidgholi, M. (2021). Geographic data-mining and extraction of association rules using the Apriori algorithm (Case study: Capital of Iranian provinces).
In Smart Sustainable Cities of the Future (pp. 189-246). Springer, Cham.‏
Javan, F., Afrakhteh, H. and Riyahi, V. (2019). Spatial Analysis of Tourism Impacts on the Economy of Rural Areas (Case Study: Rezvanshahr County, Iran). Journal of Research and Rural Planning, 8(3), 133-150. doi: 10.22067/jrrp.v8i3.80895
Javan,F. and Pourgharib,B. (2024). Assessing the Impact of English Language Proficiency in Host Communities on the Sustainability of Rural Tourism(A Case Study of Villages in Gilan Province, Northern Iran). journal of sustainable rural development, 8(1), 119-130. doi: 10.22034/jsrd.2024.458005.1187
Krzysztofik, R. (2016). Revisiting the question of centripetal and centrifugal forces in urban systems. Geographia Polonica, 89(4), 429-442.
Martin, D., & Grodach, C. (2022). Placing production in urban cultural policy: The locational patterns of cultural industries and related manufacturing. Journal of Urban Affairs, 44(4-5), 567-587.
Mohamadi, M., Afrakhteh, H. and Javan, F. (2022). Performance Evaluation of the Modern Rural Management based on Good Governance Approach (Case Study: Villages in Central District of Karaj County). Journal of Research and Rural Planning, 11(1), 59-79. doi: 10.22067/JRRP.V11I1.2108.1021
Nong, D. H., Lepczyk, C. A., Miura, T., & Fox, J. M. (2018). Quantifying urban growth patterns in Hanoi using landscape expansion modes and time series spatial metrics. PloS one, 13(5), e0196940.
Pampoore-Thampi, A., Varde, A., & Yu, D. (2014). Mining GIS data to predict urban sprawl. ACM KDD (Bloomberg Track), 118-125.
Panigrahi, S., Verma, K., & Tripathi, P. (2017). Data mining algorithms for land cover change detection: a review. Sādhanā, 42, 2081-2097.
Panigrahi, S., Verma, K., & Tripathi, P. (2021). Review of MODIS EVI and NDVI data for data mining applications. In Data Deduplication Approaches (pp. 231-253). Academic Press.
Rasmussen, L. V., Fold, N., Olesen, R. S., & Shackleton, S. (2021). Socio-economic outcomes of ecological infrastructure investments. Ecosystem Services, 47, 101242.
Rodrigue, J. P. (2020). The geography of transport systems. Routledge.
Schneider, A. (2012). Monitoring land cover change in urban and peri-urban areas using dense time stacks of Landsat satellite data and a data mining approach. Remote Sensing of Environment, 124, 689-704.
Shekhar, S., Zhang, P., & Huang, Y. (2010). Spatial data mining. Data mining and knowledge discovery handbook, 837-854.
Sundarakumar, K., M. Harika, S.A. Begum, S. Yamini and K. Balakrishna. 2012. Land Use and Land Cover Change Detection and Urban Sprawl Analysis of Vijayawada City Using a Landsat Data. Engineering Science & Technology, 4: 170-178
Tayyebi, A., & Pijanowski, B. C. (2014). Modeling multiple land use changes using ANN, CART and MARS: Comparing tradeoffs in goodness of fit and explanatory power of data mining tools. International Journal of Applied Earth Observation and Geoinformation, 28, 102-116.
Wang, Deren Li · Shuliang &Deyi Li., & Li, D. (2015) Spatial data mining. Berlin, Heidelberg: Springer Berlin Heidelberg.
Zeng, L., Wang, B., Fan, L., & Wu, J. (2016). Analyzing sustainability of Chinese mining cities using an association rule mining approach. Resources Policy, 49, 394-404.
Preipheral Urban Spaces Development
Volume 7, Issue 3 - Serial Number 17
Autumn
Autumn 2025
Pages 179-210